arXiv subjects

Zhensheng Wang

Publications and source records attributed to Zhensheng Wang.

8 recordsLinked to original sources

arXiv2026

STQA: A Benchmark for Stock-Focused Tabular Question Answering over Historical and Forecasted Data

Stock market analysis inherently requires composite reasoning over historical records and future projections, yet existing benchmarks remain fragmented across isolated tasks. We introduce STQA (Stock-focused Tabular Question Answering), an end-to-end benchmark designed to systematically evaluate natural-language question answering over historical data, numerical forecasts, and forecast-based reasoning. Built on a large-scale financial dataset, STQA covers 4,417 stocks and contains 31,400 question-answer pairs derived from expert-crafted templates, accompanied by fine-grained intent and slot annotations. To operationalize this benchmark, we present SQFRS (Stock Query-Forecast-Reasoning System), an agent-based unified framework that orchestrates SQL retrieval and time-series forecasting tools. Experiments demonstrate that while current large language models perform well on historical queries, forecast-based reasoning poses a substantial challenge, revealing critical bottlenecks in tool coordination and reasoning under uncertainty. The dataset and code are available at https://github.com/xuxubaobaoan/STQA_Project. STQA thus serves as a rigorous testbed for future research on trustworthy, tool-augmented financial agents.

cs.CL↗

arXiv2026

ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning

The rapid development of LLMs has significantly advanced tabular question answering, but most systems cannot perform future-oriented numerical prediction. To address this gap, we introduce a novel task, Open-Domain Tabular Question Answering for Future Data Forecasting and Reasoning, and propose the first dataset to cover time-series forecasting and forecast-based reasoning scenarios using real estate data. This task poses challenges in retrieving precise historical data, overcoming the forecasting limitations of LLMs, and standardizing responses for diverse queries. To solve the above challenges, we propose TimeFore, an LLM agent-based framework that decomposes the problem into three collaborative roles: a Retriever autonomously generates SQL to fetch data, a Forecaster invokes external time-series models for higher accuracy, and an Analyzer synthesizes the results to construct a precise and consistent final answer. Extensive experiments demonstrate the effectiveness of our TimeFore.

cs.IR↗

arXiv2026

BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting

Quantitative backtesting is essential for evaluating trading strategies but remains hampered by high technical barriers and limited scalability. While Large Language Models (LLMs) offer a transformative path to automate this complex, interdisciplinary workflow through advanced code generation, tool usage, and agentic planning, the practical realization is significantly challenged by the current lack of a large-scale benchmark dedicated to automated quantitative backtesting, which hinders progress in this field. To bridge this critical gap, we introduce BacktestBench, the first large-scale benchmark for automated quantitative backtesting. Built from over 6 million real market records, it comprises 18,246 meticulously annotated question-answering pairs across four task categories: metrics calculation, ticker selection, strategy selection, and parameter confirmation. We also propose AutoBacktest, a robust multi-agent baseline that translates natural language strategies into reproducible backtests by coordinating a Summarizer for semantic factor extraction, a Retriever for validated SQL generation, and a Coder for Python backtesting implementation. Our evaluation on 23 mainstream LLMs, complemented by targeted ablations, identifies key factors that influence end-to-end performance and highlights the importance of grounded verification and standardized indicator representations.

cs.CL↗

arXiv2026

Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions

Presentation slides are a primary medium for data-driven reporting, yet keeping complex, analytics-style decks up to date remains labor-intensive. Existing automation methods mostly follow fixed template filling and cannot support dynamic updates for diverse, user-authored slide decks. We therefore define "Dynamic Slide Update via Natural Language Instructions on User-provided Templates" and introduce DynaSlide, a large-scale benchmark with 20,036 real-world instruction-execution triples (source slide, user instruction, target slide) grounded in a shared external database and built from business reporting slides under bring-your-own-template (BYO-template) conditions. To tackle this task, we propose SlideAgent, an agent-based framework that combines multimodal slide parsing, natural language instruction grounding, and tool-augmented reasoning for tables, charts, and textual conclusions. SlideAgent updates content while preserving layout and style, providing a strong reference baseline on DynaSlide. We further design end-to-end and component-level evaluation protocols that reveal key challenges and opportunities for future research. The dataset and code are available at https://github.com/XiaoZhou2024/SlideAgent.

cs.CL↗

arXiv2026

ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification

The advancement of large language models (LLMs) has enhanced tabular question answering (Tabular QA), yet they struggle with open-domain queries exhibiting underspecified or uncertain expressions. To address this, we introduce the ODUTQA-MDC task and the first comprehensive benchmark to tackle it. This benchmark includes: (1) a large-scale ODUTQA dataset with 209 tables and 25,105 QA pairs; (2) a fine-grained labeling scheme for detailed evaluation; and (3) a dynamic clarification interface that simulates user feedback for interactive assessment. We also propose MAIC-TQA, a multi-agent framework that excels at detecting ambiguities, clarifying them through dialogue, and refining answers. Experiments validate our benchmark and framework, establishing them as a key resource for advancing conversational, underspecification-aware Tabular QA research.

cs.CL↗

arXiv2026

EVGeoQA: Benchmarking LLMs on Dynamic, Multi-Objective Geo-Spatial Exploration

While Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, their potential for purpose-driven exploration in dynamic geo-spatial environments remains under-investigated. Existing Geo-Spatial Question Answering (GSQA) benchmarks predominantly focus on static retrieval, failing to capture the complexity of real-world planning that involves dynamic user locations and compound constraints. To bridge this gap, we introduce EVGeoQA, a novel benchmark built upon Electric Vehicle (EV) charging scenarios that features a distinct location-anchored and dual-objective design. Specifically, each query in EVGeoQA is explicitly bound to a user's real-time coordinate and integrates the dual objectives of a charging necessity and a co-located activity preference. To systematically assess models in such complex settings, we further propose GeoRover, a general evaluation framework based on a tool-augmented agent architecture to evaluate the LLMs' capacity for dynamic, multi-objective exploration. Our experiments reveal that while LLMs successfully utilize tools to address sub-tasks, they struggle with long-range spatial exploration. Notably, we observe an emergent capability: LLMs can summarize historical exploration trajectories to enhance exploration efficiency. These findings establish EVGeoQA as a challenging testbed for future geo-spatial intelligence. The dataset and prompts are available at https://github.com/kg-bnu/EVGeoQA.

cs.AI↗

arXiv2025

RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sector

The real estate market relies heavily on structured data, such as property details, market trends, and price fluctuations. However, the lack of specialized Tabular Question Answering datasets in this domain limits the development of automated question-answering systems. To fill this gap, we introduce RETQA, the first large-scale open-domain Chinese Tabular Question Answering dataset for Real Estate. RETQA comprises 4,932 tables and 20,762 question-answer pairs across 16 sub-fields within three major domains: property information, real estate company finance information and land auction information. Compared with existing tabular question answering datasets, RETQA poses greater challenges due to three key factors: long-table structures, open-domain retrieval, and multi-domain queries. To tackle these challenges, we propose the SLUTQA framework, which integrates large language models with spoken language understanding tasks to enhance retrieval and answering accuracy. Extensive experiments demonstrate that SLUTQA significantly improves the performance of large language models on RETQA by in-context learning. RETQA and SLUTQA provide essential resources for advancing tabular question answering research in the real estate domain, addressing critical challenges in open-domain and long-table question-answering. The dataset and code are publicly available at \url{https://github.com/jensen-w/RETQA}.

cs.CL↗

arXiv2024

CosIn: A Statistical-based Algorithm for Computation of Space-speed Time Delay in Pedestrian Motion

Precise assessment of Space-speed time delay (TD) is critical for distinguishing between anticipation and reaction behaviors within pedestrian motion. Besides, the TD scale is instrumental in the evaluation of potential collision tendency of the crowd, thereby providing essential quantitative metrics for assessing risk. In this consideration, this paper introduced the CosIn algorithm for evaluating TD during pedestrian motion, which includes both the CosIn-1 and CosIn-2 algorithms. CosIn-1 algorithm analytically calculates TD, replacing the numerical method of discrete cross-correlation, whereas the CosIn-2 algorithm estimates the TD from a statistical perspective. Specifically, the CosIn-1 algorithm addresses the precise computation of TD for individual pedestrians, while the CosIn-2 algorithm is employed for assessing TD at the crowd scale, concurrently addressing the imperative of real-time evaluation. Efficacy analyses of the CosIn-1 and CosIn-2 algorithms are conducted with data from single-file pedestrian experiments and crowd-crossing experiments, respectively. During this process, the discrete cross-correlation method was employed as a baseline to evaluate the performance of both algorithms, which demonstrated notable accuracy. This algorithm facilitate the precise evaluation of behavior patterns and collision tendency within crowds, thereby enabling us to understand the crowds dynamics from a new perspective.

physics.soc-ph↗